Face Generation

In this project, you'll use generative adversarial networks to generate new images of faces.

Get the Data

You'll be using two datasets in this project:

  • MNIST
  • CelebA

Since the celebA dataset is complex and you're doing GANs in a project for the first time, we want you to test your neural network on MNIST before CelebA. Running the GANs on MNIST will allow you to see how well your model trains sooner.

If you're using FloydHub, set data_dir to "/input" and use the FloydHub data ID "R5KrjnANiKVhLWAkpXhNBe".

In [1]:
data_dir = './data'

# FloydHub - Use with data ID "R5KrjnANiKVhLWAkpXhNBe"
#data_dir = '/input'


"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import helper

helper.download_extract('mnist', data_dir)
helper.download_extract('celeba', data_dir)
Found mnist Data
Found celeba Data

Explore the Data

MNIST

As you're aware, the MNIST dataset contains images of handwritten digits. You can view the first number of examples by changing show_n_images.

In [2]:
show_n_images = 25

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
%matplotlib inline
import os
from glob import glob
from matplotlib import pyplot

mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'mnist/*.jpg'))[:show_n_images], 28, 28, 'L')
pyplot.imshow(helper.images_square_grid(mnist_images, 'L'), cmap='gray')
Out[2]:
<matplotlib.image.AxesImage at 0x7f6e23e30cf8>

CelebA

The CelebFaces Attributes Dataset (CelebA) dataset contains over 200,000 celebrity images with annotations. Since you're going to be generating faces, you won't need the annotations. You can view the first number of examples by changing show_n_images.

In [3]:
show_n_images = 100

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'img_align_celeba/*.jpg'))[:show_n_images], 28, 28, 'RGB')
pyplot.imshow(helper.images_square_grid(mnist_images, 'RGB'))
Out[3]:
<matplotlib.image.AxesImage at 0x7f6e215dcdd8>

Preprocess the Data

Since the project's main focus is on building the GANs, we'll preprocess the data for you. The values of the MNIST and CelebA dataset will be in the range of -0.5 to 0.5 of 28x28 dimensional images. The CelebA images will be cropped to remove parts of the image that don't include a face, then resized down to 28x28.

The MNIST images are black and white images with a single color channel while the CelebA images have 3 color channels (RGB color channel).

Build the Neural Network

You'll build the components necessary to build a GANs by implementing the following functions below:

  • model_inputs
  • discriminator
  • generator
  • model_loss
  • model_opt
  • train

Check the Version of TensorFlow and Access to GPU

This will check to make sure you have the correct version of TensorFlow and access to a GPU

In [4]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
from distutils.version import LooseVersion
import warnings
import tensorflow as tf

# Check TensorFlow Version
assert LooseVersion(tf.__version__) >= LooseVersion('1.0'), 'Please use TensorFlow version 1.0 or newer.  You are using {}'.format(tf.__version__)
print('TensorFlow Version: {}'.format(tf.__version__))

# Check for a GPU
if not tf.test.gpu_device_name():
    warnings.warn('No GPU found. Please use a GPU to train your neural network.')
else:
    print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))
TensorFlow Version: 1.2.0
Default GPU Device: /gpu:0

Input

Implement the model_inputs function to create TF Placeholders for the Neural Network. It should create the following placeholders:

  • Real input images placeholder with rank 4 using image_width, image_height, and image_channels.
  • Z input placeholder with rank 2 using z_dim.
  • Learning rate placeholder with rank 0.

Return the placeholders in the following the tuple (tensor of real input images, tensor of z data)

In [5]:
import problem_unittests as tests

def model_inputs(image_width, image_height, image_channels, z_dim):
    """
    Create the model inputs
    :param image_width: The input image width
    :param image_height: The input image height
    :param image_channels: The number of image channels
    :param z_dim: The dimension of Z
    :return: Tuple of (tensor of real input images, tensor of z data, learning rate)
    """
    # TODO: Implement Function
    input_real = tf.placeholder(tf.float32,shape=(None,image_width,image_height,image_channels), name ="input_real")
    input_z = tf.placeholder(tf.float32,shape=(None,z_dim), name ="input_z")
    learning_rate = tf.placeholder(tf.float32,name="learning_rate")

    return input_real, input_z, learning_rate


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_inputs(model_inputs)
ERROR:tensorflow:==================================
Object was never used (type <class 'tensorflow.python.framework.ops.Operation'>):
<tf.Operation 'assert_rank_2/Assert/Assert' type=Assert>
If you want to mark it as used call its "mark_used()" method.
It was originally created here:
['File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/runpy.py", line 193, in _run_module_as_main\n    "__main__", mod_spec)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/runpy.py", line 85, in _run_code\n    exec(code, run_globals)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/ipykernel_launcher.py", line 16, in <module>\n    app.launch_new_instance()', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance\n    app.start()', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/ipykernel/kernelapp.py", line 477, in start\n    ioloop.IOLoop.instance().start()', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/zmq/eventloop/ioloop.py", line 177, in start\n    super(ZMQIOLoop, self).start()', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/tornado/ioloop.py", line 888, in start\n    handler_func(fd_obj, events)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper\n    return fn(*args, **kwargs)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events\n    self._handle_recv()', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv\n    self._run_callback(callback, msg)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback\n    callback(*args, **kwargs)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper\n    return fn(*args, **kwargs)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 283, in dispatcher\n    return self.dispatch_shell(stream, msg)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell\n    handler(stream, idents, msg)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 399, in execute_request\n    user_expressions, allow_stdin)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/ipykernel/ipkernel.py", line 196, in do_execute\n    res = shell.run_cell(code, store_history=store_history, silent=silent)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/ipykernel/zmqshell.py", line 533, in run_cell\n    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2698, in run_cell\n    interactivity=interactivity, compiler=compiler, result=result)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2808, in run_ast_nodes\n    if self.run_code(code, result):', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2862, in run_code\n    exec(code_obj, self.user_global_ns, self.user_ns)', 'File "<ipython-input-5-fdf20db26000>", line 23, in <module>\n    tests.test_model_inputs(model_inputs)', 'File "/home/carnd/deep-learning/face_generation/problem_unittests.py", line 12, in func_wrapper\n    result = func(*args)', 'File "/home/carnd/deep-learning/face_generation/problem_unittests.py", line 68, in test_model_inputs\n    _check_input(learn_rate, [], \'Learning Rate\')', 'File "/home/carnd/deep-learning/face_generation/problem_unittests.py", line 34, in _check_input\n    _assert_tensor_shape(tensor, shape, \'Real Input\')', 'File "/home/carnd/deep-learning/face_generation/problem_unittests.py", line 20, in _assert_tensor_shape\n    assert tf.assert_rank(tensor, len(shape), message=\'{} has wrong rank\'.format(display_name))', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/tensorflow/python/ops/check_ops.py", line 617, in assert_rank\n    dynamic_condition, data, summarize)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/tensorflow/python/ops/check_ops.py", line 571, in _assert_rank_condition\n    return control_flow_ops.Assert(condition, data, summarize=summarize)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 170, in wrapped\n    return _add_should_use_warning(fn(*args, **kwargs))', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 139, in _add_should_use_warning\n    wrapped = TFShouldUseWarningWrapper(x)', 'File "/home/carnd/anaconda3/envs/dl5/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 96, in __init__\n    stack = [s.strip() for s in traceback.format_stack()]']
==================================
Tests Passed

Discriminator

Implement discriminator to create a discriminator neural network that discriminates on images. This function should be able to reuse the variabes in the neural network. Use tf.variable_scope with a scope name of "discriminator" to allow the variables to be reused. The function should return a tuple of (tensor output of the discriminator, tensor logits of the discriminator).

In [6]:
def discriminator(images, reuse=False):
    """
    Create the discriminator network
    :param image: Tensor of input image(s)
    :param reuse: Boolean if the weights should be reused
    :return: Tuple of (tensor output of the discriminator, tensor logits of the discriminator)
    """
    # TODO: Implement Function
    with tf.variable_scope('discriminator',reuse = reuse):
        #Input layer is 28*28*3
        x1 = tf.layers.conv2d(images,128,5,strides=2,padding='same')
        relu1 = tf.maximum(0.2*x1,x1)
        #14*14*64
        print('relu1')
        print(x1.shape)
        
        x2 = tf.layers.conv2d(relu1,256,5,strides=2,padding='same')
        bn2 = tf.layers.batch_normalization(x2,training=True)
        relu2 = tf.maximum(0.2*bn2,bn2)
        #7*7*128
        print('relu2')
        print(relu2.shape)
        
        x3 = tf.layers.conv2d(relu2,512,5,strides=2,padding='same')
        bn3 = tf.layers.batch_normalization(x3,training=True)
        relu3 = tf.maximum(0.2*bn3,bn3)
        #4*4*256 
        print('relu3')
        print(relu3.shape)
        
        flat = tf.reshape(relu3,(-1,4*4*512))
        logits = tf.layers.dense(flat,1)
        out = tf.sigmoid(logits)

    return out, logits


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_discriminator(discriminator, tf)
relu1
(?, 14, 14, 128)
relu2
(?, 7, 7, 256)
relu3
(?, 4, 4, 512)
relu1
(?, 14, 14, 128)
relu2
(?, 7, 7, 256)
relu3
(?, 4, 4, 512)
Tests Passed

Generator

Implement generator to generate an image using z. This function should be able to reuse the variabes in the neural network. Use tf.variable_scope with a scope name of "generator" to allow the variables to be reused. The function should return the generated 28 x 28 x out_channel_dim images.

In [7]:
def generator(z, out_channel_dim, is_train=True):
    """
    Create the generator network
    :param z: Input z
    :param out_channel_dim: The number of channels in the output image
    :param is_train: Boolean if generator is being used for training
    :return: The tensor output of the generator
    """
    # TODO: Implement Function
    with tf.variable_scope('generator',reuse=not is_train):
        alpha = 0.2
        x1 = tf.layers.dense(z,4*4*512)
        #reshape to start the convolutional stack
        x1 = tf.reshape(x1,(-1,4,4,512))
        x1 = tf.layers.batch_normalization(x1, training=is_train)
        x1 = tf.maximum(alpha*x1,x1)
        #4*4*512 now
        print ('x1')
        print (x1.shape)
        
        x2 = tf.layers.conv2d_transpose(x1, 256, 4 ,strides=1,padding='valid')
        x2 = tf.layers.batch_normalization(x2,training=is_train)
        x2 = tf.maximum(alpha*x2,x2)
        #7*7*256 now
        print ('x2')
        print (x2.shape)
        
        x3 = tf.layers.conv2d_transpose(x2, 128, 5 ,strides=2,padding='same')
        x3 = tf.layers.batch_normalization(x3,training=is_train)
        x3 = tf.maximum(alpha*x3,x3)
        #14*14*128 now
        print ('x3')
        print (x3.shape)

        x4 = tf.layers.conv2d_transpose(x3, 64, 5 ,strides=1,padding='same')
        x4 = tf.layers.batch_normalization(x4,training=is_train)
        x4 = tf.maximum(alpha*x4,x4)
        #28*28*64 now
        print ('x4')
        print (x4.shape)
        
        logits =tf.layers.conv2d_transpose(x4, out_channel_dim ,5,strides=2,padding='same')
        #28*28*3 now
        print ('logits')
        print (logits.shape)
        
        out  = tf.tanh(logits)
           
    return out


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_generator(generator, tf)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 5)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 5)
Tests Passed

Loss

Implement model_loss to build the GANs for training and calculate the loss. The function should return a tuple of (discriminator loss, generator loss). Use the following functions you implemented:

  • discriminator(images, reuse=False)
  • generator(z, out_channel_dim, is_train=True)
In [8]:
def model_loss(input_real, input_z, out_channel_dim):
    """
    Get the loss for the discriminator and generator
    :param input_real: Images from the real dataset
    :param input_z: Z input
    :param out_channel_dim: The number of channels in the output image
    :return: A tuple of (discriminator loss, generator loss)
    """
    # TODO: Implement Function
    g_model = generator(input_z,out_channel_dim)
    d_model_real, d_logits_real = discriminator(input_real)
    d_model_fake, d_logits_fake = discriminator(g_model, reuse = True)
    #nm can be improved
    d_loss_real = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_real, labels=tf.ones_like(d_model_real)) )
    d_loss_fake = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.zeros_like(d_model_fake)))
    g_loss = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.ones_like(d_model_fake)))

    d_loss = d_loss_real + d_loss_fake
        
    return d_loss, g_loss


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_loss(model_loss)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 4)
relu1
(?, 14, 14, 128)
relu2
(?, 7, 7, 256)
relu3
(?, 4, 4, 512)
relu1
(?, 14, 14, 128)
relu2
(?, 7, 7, 256)
relu3
(?, 4, 4, 512)
Tests Passed

Optimization

Implement model_opt to create the optimization operations for the GANs. Use tf.trainable_variables to get all the trainable variables. Filter the variables with names that are in the discriminator and generator scope names. The function should return a tuple of (discriminator training operation, generator training operation).

In [9]:
def model_opt(d_loss, g_loss, learning_rate, beta1):
    """
    Get optimization operations
    :param d_loss: Discriminator loss Tensor
    :param g_loss: Generator loss Tensor
    :param learning_rate: Learning Rate Placeholder
    :param beta1: The exponential decay rate for the 1st moment in the optimizer
    :return: A tuple of (discriminator training operation, generator training operation)
    """
    # TODO: Implement Function
    t_vars = tf.trainable_variables()
    d_vars = [var for var in t_vars if var.name.startswith('discriminator')]
    g_vars = [var for var in t_vars if var.name.startswith('generator')]
    
    #Optimize
    with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
        d_train_opt = tf.train.AdamOptimizer(learning_rate,beta1=beta1).minimize(d_loss,var_list=d_vars)
        g_train_opt = tf.train.AdamOptimizer(learning_rate,beta1=beta1).minimize(g_loss,var_list=g_vars)
    return d_train_opt, g_train_opt


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_opt(model_opt, tf)
Tests Passed

Neural Network Training

Show Output

Use this function to show the current output of the generator during training. It will help you determine how well the GANs is training.

In [10]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import numpy as np

def show_generator_output(sess, n_images, input_z, out_channel_dim, image_mode):
    """
    Show example output for the generator
    :param sess: TensorFlow session
    :param n_images: Number of Images to display
    :param input_z: Input Z Tensor
    :param out_channel_dim: The number of channels in the output image
    :param image_mode: The mode to use for images ("RGB" or "L")
    """
    cmap = None if image_mode == 'RGB' else 'gray'
    z_dim = input_z.get_shape().as_list()[-1]
    example_z = np.random.uniform(-1, 1, size=[n_images, z_dim])

    samples = sess.run(
        generator(input_z, out_channel_dim, False),
        feed_dict={input_z: example_z})

    images_grid = helper.images_square_grid(samples, image_mode)
    pyplot.imshow(images_grid, cmap=cmap)
    pyplot.show()

Train

Implement train to build and train the GANs. Use the following functions you implemented:

  • model_inputs(image_width, image_height, image_channels, z_dim)
  • model_loss(input_real, input_z, out_channel_dim)
  • model_opt(d_loss, g_loss, learning_rate, beta1)

Use the show_generator_output to show generator output while you train. Running show_generator_output for every batch will drastically increase training time and increase the size of the notebook. It's recommended to print the generator output every 100 batches.

In [11]:
def train(epoch_count, batch_size, z_dim, learning_rate, beta1, get_batches, data_shape, data_image_mode):
    """
    Train the GAN
    :param epoch_count: Number of epochs
    :param batch_size: Batch Size
    :param z_dim: Z dimension
    :param learning_rate: Learning Rate
    :param beta1: The exponential decay rate for the 1st moment in the optimizer
    :param get_batches: Function to get batches
    :param data_shape: Shape of the data
    :param data_image_mode: The image mode to use for images ("RGB" or "L")
    """
    # TODO: Build Model
    _, image_width, image_height, image_channels = data_shape
    input_real, input_z, lr = model_inputs(image_width, image_height, image_channels, z_dim)
    d_loss, g_loss = model_loss(input_real, input_z, image_channels)
    d_opt,g_opt = model_opt(d_loss, g_loss, learning_rate, beta1)
    
    steps = 0
    print_every = 50
    show_every = 25
    losses = []
    n_images = 25 
   
    
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        for epoch_i in range(epoch_count):
            for batch_images in get_batches(batch_size):
                # TODO: Train Model
                steps = steps+1
                batch_images = batch_images * 2.0                
                             
                # Random Noise for G
                batch_z = np.random.uniform(-1,1,size=(batch_size,z_dim))
                
                # Run Optimizers
                _ = sess.run(d_opt, feed_dict = {input_real:batch_images, input_z:batch_z, lr:learning_rate})
                _ = sess.run(g_opt, feed_dict = {input_real:batch_images,input_z:batch_z, lr:learning_rate})
                
                if steps % print_every ==0:
                    train_loss_d = d_loss.eval({input_z:batch_z, input_real:batch_images})
                    train_loss_g = g_loss.eval({input_z:batch_z})
                    
                    print("Epoch {}/{}..." .format(epoch_i+1,epoch_count),
                    "Discriminator Loss: {:.4f}..." .format(train_loss_d),
                    "Generator Loss: {:.4f}" .format(train_loss_g))
                    
                    losses.append((train_loss_d,train_loss_g))
                
                if steps % show_every == 0:
                    show_generator_output(sess, n_images, input_z, image_channels, data_image_mode)
                
                
                    
                    
                
                

MNIST

Test your GANs architecture on MNIST. After 2 epochs, the GANs should be able to generate images that look like handwritten digits. Make sure the loss of the generator is lower than the loss of the discriminator or close to 0.

In [12]:
batch_size = 32
z_dim = 100
learning_rate = .0008
beta1 = 0.5


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 2

mnist_dataset = helper.Dataset('mnist', glob(os.path.join(data_dir, 'mnist/*.jpg')))
with tf.Graph().as_default():
    train(epochs, batch_size, z_dim, learning_rate, beta1, mnist_dataset.get_batches,
          mnist_dataset.shape, mnist_dataset.image_mode)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
relu1
(?, 14, 14, 128)
relu2
(?, 7, 7, 256)
relu3
(?, 4, 4, 512)
relu1
(?, 14, 14, 128)
relu2
(?, 7, 7, 256)
relu3
(?, 4, 4, 512)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.7269... Generator Loss: 8.9001
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.1250... Generator Loss: 3.2239
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 2.7866... Generator Loss: 0.6266
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.6822... Generator Loss: 0.5886
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 2.2274... Generator Loss: 3.8307
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.6527... Generator Loss: 2.3217
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.7674... Generator Loss: 1.4714
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.3753... Generator Loss: 0.9630
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.3097... Generator Loss: 2.2668
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.8153... Generator Loss: 1.5727
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.1980... Generator Loss: 0.6640
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.9168... Generator Loss: 0.2997
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.2482... Generator Loss: 0.5028
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.1169... Generator Loss: 0.6793
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 2.1957... Generator Loss: 2.9598
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.3157... Generator Loss: 2.0358
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.6433... Generator Loss: 1.4479
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.1179... Generator Loss: 0.9022
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.0884... Generator Loss: 0.6566
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.3451... Generator Loss: 0.4998
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.6762... Generator Loss: 2.6869
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.7299... Generator Loss: 2.0327
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.1247... Generator Loss: 0.6631
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.5072... Generator Loss: 0.3586
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.9446... Generator Loss: 0.7639
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.0259... Generator Loss: 1.4402
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.3097... Generator Loss: 0.4179
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.9421... Generator Loss: 0.9512
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.8142... Generator Loss: 0.2294
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.8423... Generator Loss: 1.2350
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.8117... Generator Loss: 1.0818
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 2.0549... Generator Loss: 4.3048
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.7364... Generator Loss: 1.2763
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 2.4304... Generator Loss: 0.1236
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.1661... Generator Loss: 0.7799
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 0.9288... Generator Loss: 1.8544
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 1/2... Discriminator Loss: 1.0582... Generator Loss: 0.7398
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.2020... Generator Loss: 0.5799
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.9253... Generator Loss: 0.8742
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.8718... Generator Loss: 1.2663
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.6005... Generator Loss: 1.8678
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.9066... Generator Loss: 1.3372
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.6199... Generator Loss: 0.3000
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.5152... Generator Loss: 0.4280
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.9930... Generator Loss: 0.6804
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.6164... Generator Loss: 1.1410
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.2155... Generator Loss: 2.4751
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.4963... Generator Loss: 0.4048
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.6915... Generator Loss: 2.3344
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.9308... Generator Loss: 1.0847
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.2965... Generator Loss: 0.4717
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.8230... Generator Loss: 1.2572
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.1975... Generator Loss: 0.5601
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.6716... Generator Loss: 0.8837
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.4685... Generator Loss: 2.7958
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.5237... Generator Loss: 1.5226
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.8124... Generator Loss: 0.9981
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 2.5393... Generator Loss: 0.1355
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.3157... Generator Loss: 0.5145
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 2.8345... Generator Loss: 0.1324
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.9836... Generator Loss: 0.7449
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.9007... Generator Loss: 0.7929
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.7940... Generator Loss: 0.4867
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.4184... Generator Loss: 1.5728
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.3042... Generator Loss: 2.6625
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.5333... Generator Loss: 1.1585
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.6512... Generator Loss: 0.3555
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.4895... Generator Loss: 1.6147
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.7301... Generator Loss: 1.2205
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.0438... Generator Loss: 4.4628
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.4274... Generator Loss: 1.7515
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.7793... Generator Loss: 0.4092
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 1.3773... Generator Loss: 0.6058
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 3.0235... Generator Loss: 0.1314
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)
Epoch 2/2... Discriminator Loss: 0.7501... Generator Loss: 1.3264
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 1)

CelebA

Run your GANs on CelebA. It will take around 20 minutes on the average GPU to run one epoch. You can run the whole epoch or stop when it starts to generate realistic faces.

In [13]:
batch_size = 32
z_dim = 100
learning_rate = 0.0002
beta1 = 0.5


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 1

celeba_dataset = helper.Dataset('celeba', glob(os.path.join(data_dir, 'img_align_celeba/*.jpg')))
with tf.Graph().as_default():
    train(epochs, batch_size, z_dim, learning_rate, beta1, celeba_dataset.get_batches,
          celeba_dataset.shape, celeba_dataset.image_mode)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
relu1
(?, 14, 14, 128)
relu2
(?, 7, 7, 256)
relu3
(?, 4, 4, 512)
relu1
(?, 14, 14, 128)
relu2
(?, 7, 7, 256)
relu3
(?, 4, 4, 512)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.1539... Generator Loss: 11.4360
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 3.1650... Generator Loss: 0.0554
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.1936... Generator Loss: 2.9449
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.4834... Generator Loss: 1.3029
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.4791... Generator Loss: 2.8753
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.5793... Generator Loss: 7.0493
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.3622... Generator Loss: 1.8204
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8420... Generator Loss: 0.8861
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8370... Generator Loss: 1.1090
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.9846... Generator Loss: 0.9345
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6156... Generator Loss: 1.4352
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.5853... Generator Loss: 3.7428
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.4580... Generator Loss: 1.4310
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6636... Generator Loss: 1.2573
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.9618... Generator Loss: 0.9282
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7527... Generator Loss: 1.1785
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.4997... Generator Loss: 2.0187
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.4354... Generator Loss: 2.6991
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8753... Generator Loss: 2.2189
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6688... Generator Loss: 1.4060
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1195... Generator Loss: 0.6278
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7046... Generator Loss: 1.9292
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7346... Generator Loss: 1.0030
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7671... Generator Loss: 2.1978
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.9280... Generator Loss: 0.8104
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.0095... Generator Loss: 0.7457
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.2762... Generator Loss: 2.6248
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8077... Generator Loss: 0.9433
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.9655... Generator Loss: 2.0138
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8148... Generator Loss: 1.1970
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.5982... Generator Loss: 1.4329
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7740... Generator Loss: 1.6452
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8563... Generator Loss: 1.2332
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6519... Generator Loss: 1.2818
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7216... Generator Loss: 1.7970
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1265... Generator Loss: 0.6362
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8097... Generator Loss: 1.0576
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6507... Generator Loss: 2.2185
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.3286... Generator Loss: 0.4488
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.4115... Generator Loss: 0.4257
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8025... Generator Loss: 0.8363
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8224... Generator Loss: 1.7046
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.0228... Generator Loss: 2.3791
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7361... Generator Loss: 0.9617
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6392... Generator Loss: 1.3062
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7208... Generator Loss: 1.0280
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7053... Generator Loss: 0.8870
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.2264... Generator Loss: 4.2479
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7983... Generator Loss: 1.1782
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6476... Generator Loss: 1.2656
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1566... Generator Loss: 0.5127
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7478... Generator Loss: 1.6175
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7353... Generator Loss: 2.1726
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6934... Generator Loss: 1.8940
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.9407... Generator Loss: 0.9311
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.5101... Generator Loss: 1.5367
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6770... Generator Loss: 1.0297
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8201... Generator Loss: 1.7374
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1487... Generator Loss: 0.4913
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.5723... Generator Loss: 1.6537
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8674... Generator Loss: 1.6942
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7238... Generator Loss: 0.9395
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.3557... Generator Loss: 0.4776
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.4719... Generator Loss: 1.8332
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7448... Generator Loss: 1.3731
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7816... Generator Loss: 1.6742
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.7027... Generator Loss: 0.2769
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6224... Generator Loss: 1.5039
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7564... Generator Loss: 1.1314
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8853... Generator Loss: 1.2334
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6457... Generator Loss: 1.5732
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8565... Generator Loss: 2.4243
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.2116... Generator Loss: 0.5402
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1241... Generator Loss: 0.5714
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7979... Generator Loss: 1.3579
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6805... Generator Loss: 1.0608
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.5494... Generator Loss: 2.1449
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6993... Generator Loss: 1.2703
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7210... Generator Loss: 1.7078
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6587... Generator Loss: 1.4532
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.0380... Generator Loss: 1.1992
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7997... Generator Loss: 0.8464
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8675... Generator Loss: 1.2172
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6882... Generator Loss: 1.4384
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.9815... Generator Loss: 1.6876
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6159... Generator Loss: 1.6605
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7653... Generator Loss: 0.9602
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.9091... Generator Loss: 1.4081
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6996... Generator Loss: 1.4624
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.5235... Generator Loss: 0.3253
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8003... Generator Loss: 0.8517
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.0261... Generator Loss: 0.7590
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1819... Generator Loss: 0.5441
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.3191... Generator Loss: 0.4081
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.5715... Generator Loss: 1.8634
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.2109... Generator Loss: 0.5389
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.2066... Generator Loss: 0.4912
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1002... Generator Loss: 0.5520
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8836... Generator Loss: 0.8313
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8414... Generator Loss: 0.8579
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.5977... Generator Loss: 1.8624
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8089... Generator Loss: 1.2780
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8146... Generator Loss: 0.9565
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6038... Generator Loss: 1.2540
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8087... Generator Loss: 0.8707
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8757... Generator Loss: 1.2586
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6284... Generator Loss: 1.4574
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1706... Generator Loss: 0.5847
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8304... Generator Loss: 2.1298
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6512... Generator Loss: 1.1111
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8176... Generator Loss: 1.0036
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1406... Generator Loss: 0.5446
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8180... Generator Loss: 0.8310
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1837... Generator Loss: 0.5113
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.2224... Generator Loss: 0.4735
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6700... Generator Loss: 1.1872
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8470... Generator Loss: 0.8771
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.9434... Generator Loss: 0.6763
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7620... Generator Loss: 0.8974
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7274... Generator Loss: 1.9355
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8714... Generator Loss: 2.1214
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.6953... Generator Loss: 1.7893
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.7315... Generator Loss: 0.9044
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 0.8441... Generator Loss: 2.8252
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.1904... Generator Loss: 0.4775
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
Epoch 1/1... Discriminator Loss: 1.0593... Generator Loss: 0.5922
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)
x1
(?, 4, 4, 512)
x2
(?, 7, 7, 256)
x3
(?, 14, 14, 128)
x4
(?, 14, 14, 64)
logits
(?, 28, 28, 3)

Submitting This Project

When submitting this project, make sure to run all the cells before saving the notebook. Save the notebook file as "dlnd_face_generation.ipynb" and save it as a HTML file under "File" -> "Download as". Include the "helper.py" and "problem_unittests.py" files in your submission.

In [ ]: